Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 17, 2025tm - Technisches Messen

Beiträge. Machine learning-based prediction of remaining useful lifetime for solder joints based on real mission profile data

View Full Paper
Ask AI
Bookmark
Share

Authors

DBDarshankumar BhatSMStefan MünchMRMike Röllig

Discussion

Loading...

Member takes

Overview

Methodology estimates remaining useful lifetime of solder joints under mission profile loads, suggesting effective condition-based maintenance strategies.

Key Points

  • Solder joints can accurately predict fatigue increments, enhancing reliability in electronic systems using machine learning models.
  • Using a multilayer perceptron, the study found an effective correlation between temperature characteristics and solder joint degradation.
  • Field data from a light rail vehicle was utilized to enhance predictions for solder joint longevity through synthetic data augmentation.
  • This methodology highlights the importance of prognostic and health monitoring frameworks in prolonging system lifespan under varied operational loads.

Cite This Study

Bhat et al. (2025) studied this question.

synapsesocial.com/papers/68a36f7d0a429f7973331df3https://doi.org/10.1515/teme-2025-0056
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Application oriented On-The-Edge Capable Prognostic and Health Monitoring Framework for Solder Joints in Electronics2024
  2. 2Physics-Informed Machine Learning for Solder Joint Qualification Tests2024
  3. 3Data-driven lifetime estimation of solder joints with various geometries2025
  4. 4Application of deep learning to predict the fatigue life of solder joints in IC packaging2026
  5. 5Hybrid modeling for remaining useful life prediction in power module prognosis2024